[v6,00/14] prohibit pinning pages in ZONE_MOVABLE

Changelog
---------
v6
  Small update, but I wanted to send it out quicker, as it removes a
  controversial patch and replaces it with something sane.
- Removed forcing FOLL_WRITE for longterm gup, instead added a patch to
  skip zero pages during migration.
- Added reviewed-by's and minor log changes.

v5
- Added the following patches to the beginning of series, which are fixes
   to the other existing problems with CMA migration code:
	mm/gup: check every subpage of a compound page during isolation
	mm/gup: return an error on migration failure
	mm/gup: check for isolation errors also at the beginning of series
	mm/gup: do not allow zero page for pinned pages
- remove .gfp_mask/.reclaim_idx changes from mm/vmscan.c
- update movable zone header comment in patch 8 instead of patch 3, fix
  the comment
- Added acked, sign-offs
- Updated commit logs based on feedback
- Addressed issues reported by Michal and Jason.
- Remove:
	#define PINNABLE_MIGRATE_MAX	10
	#define PINNABLE_ISOLATE_MAX	100
   Instead: fail on the first migration failure, and retry isolation
   forever as their failures are transient.

- In self-set addressed some of the comments from John Hubbard, updated
  commit logs, and added comments. Renamed gup->flags with gup->test_flags.

v4
- Address page migration comments. New patch:
  mm/gup: limit number of gup migration failures, honor failures
  Implements the limiting number of retries for migration failures, and
  also check for isolation failures.
  Added a test case into gup_test to verify that pages never long-term
  pinned in a movable zone, and also added tests to fault both in kernel
  and in userland.
v3
- Merged with linux-next, which contains clean-up patch from Jason,
  therefore this series is reduced by two patches which did the same
  thing.
v2
- Addressed all review comments
- Added Reviewed-by's.
- Renamed PF_MEMALLOC_NOMOVABLE to PF_MEMALLOC_PIN
- Added is_pinnable_page() to check if page can be longterm pinned
- Fixed gup fast path by checking is_in_pinnable_zone()
- rename cma_page_list to movable_page_list
- add a admin-guide note about handling pinned pages in ZONE_MOVABLE,
  updated caveat about pinned pages from linux/mmzone.h
- Move current_gfp_context() to fast-path

---------
When page is pinned it cannot be moved and its physical address stays
the same until pages is unpinned.

This is useful functionality to allows userland to implementation DMA
access. For example, it is used by vfio in vfio_pin_pages().

However, this functionality breaks memory hotplug/hotremove assumptions
that pages in ZONE_MOVABLE can always be migrated.

This patch series fixes this issue by forcing new allocations during
page pinning to omit ZONE_MOVABLE, and also to migrate any existing
pages from ZONE_MOVABLE during pinning.

It uses the same scheme logic that is currently used by CMA, and extends
the functionality for all allocations.

For more information read the discussion [1] about this problem.
[1] https://lore.kernel.org/lkml/CA+CK2bBffHBxjmb9jmSKacm0fJMinyt3Nhk8Nx6iudcQSj80_w@mail.gmail.com

Previous versions:
v1
https://lore.kernel.org/lkml/20201202052330.474592-1-pasha.tatashin@soleen.com
v2
https://lore.kernel.org/lkml/20201210004335.64634-1-pasha.tatashin@soleen.com
v3
https://lore.kernel.org/lkml/20201211202140.396852-1-pasha.tatashin@soleen.com
v4
https://lore.kernel.org/lkml/20201217185243.3288048-1-pasha.tatashin@soleen.com
v5
https://lore.kernel.org/lkml/20210119043920.155044-1-pasha.tatashin@soleen.com

Pavel Tatashin (14):
  mm/gup: don't pin migrated cma pages in movable zone
  mm/gup: check every subpage of a compound page during isolation
  mm/gup: return an error on migration failure
  mm/gup: check for isolation errors
  mm cma: rename PF_MEMALLOC_NOCMA to PF_MEMALLOC_PIN
  mm: apply per-task gfp constraints in fast path
  mm: honor PF_MEMALLOC_PIN for all movable pages
  mm/gup: do not migrate zero page
  mm/gup: migrate pinned pages out of movable zone
  memory-hotplug.rst: add a note about ZONE_MOVABLE and page pinning
  mm/gup: change index type to long as it counts pages
  mm/gup: longterm pin migration cleaup
  selftests/vm: test flag is broken
  selftests/vm: test faulting in kernel, and verify pinnable pages

 .../admin-guide/mm/memory-hotplug.rst         |   9 +
 include/linux/migrate.h                       |   1 +
 include/linux/mm.h                            |  11 ++
 include/linux/mmzone.h                        |  13 +-
 include/linux/sched.h                         |   2 +-
 include/linux/sched/mm.h                      |  27 +--
 include/trace/events/migrate.h                |   3 +-
 mm/gup.c                                      | 175 ++++++++----------
 mm/gup_test.c                                 |  29 +--
 mm/gup_test.h                                 |   3 +-
 mm/hugetlb.c                                  |   4 +-
 mm/page_alloc.c                               |  33 ++--
 tools/testing/selftests/vm/gup_test.c         |  36 +++-
 13 files changed, 185 insertions(+), 161 deletions(-)

On Wed, Jan 20, 2021 at 8:19 AM Jason Gunthorpe <jgg@ziepe.ca> wrote:
>
> On Tue, Jan 19, 2021 at 08:43:31PM -0500, Pavel Tatashin wrote:
> > When pages are longterm pinned, we must migrated them out of movable zone.
> > The function that migrates them has a hidden loop with goto. The loop is
> > to retry on isolation failures, and after successful migration.
> >
> > Make this code better by moving this loop to the caller.
> >
> > Signed-off-by: Pavel Tatashin <pasha.tatashin@soleen.com>
> >  mm/gup.c | 88 +++++++++++++++++++++++---------------------------------
> >  1 file changed, 36 insertions(+), 52 deletions(-)
>
> This looks OK, it is better
>
> Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
>
> I really dislike we always have to go over the page list twice in pin
> mode

I agree, I also dislike that we have to loop twice.

>
> The is_pinnable_page() and LRU isolation should really be done inside
> __get_user_pages_locked() as each page is added to the output list
>
> But that is more of a larger issue than this series

We could also think about adding some optimization flags, i.e. clients
could tell gup that the pinned memory content can be discarded
FOLL_DISCARD. That way we could always allocate new pages in the right
zones as we do with this series and free existing translations. No
migration check would be necessary with such a flag.

>
> Jason